Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a9f0d1597105b2ae2c4068c002b554e7fab84818ec9eb58143a840cbff4794
+oid sha256:cd457bd8c81e8920cea04d50bb8020d2937d8f99772ad0902f7e943ceb90be2a
 size 267832560

run-1/checkpoint-6414/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfba73a5198ff44975fc53ef112a335cab3999b9258b3fbf8b873f6af1e25a98
+size 267832560

run-1/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62741077ea78d726cce111b62bbe5f972e3ae1d93cf55f462e8b5bdcdbe34c01
+size 535727290

run-1/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54da1dccf9a24b2161ec0efa4e8615ce7d84d52d4247839fc92b002eb16c7b4e
+size 14244

run-1/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8ddb9f7eae7d3e02fb8a9349f8b9058c67e1d50082338a8e0d13b75fa4c15f
+size 1064

run-1/checkpoint-6414/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-6414/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-6414/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": 0.394210256729861,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-6414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.2052836418151855,
+      "learning_rate": 5.527461334920752e-05,
+      "loss": 0.6278,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5090547800064087,
+      "learning_rate": 5.1842260309639244e-05,
+      "loss": 0.6192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.86550760269165,
+      "learning_rate": 4.840990727007098e-05,
+      "loss": 0.6103,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.385833740234375,
+      "learning_rate": 4.49775542305027e-05,
+      "loss": 0.5852,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6027922034263611,
+      "eval_matthews_correlation": 0.15833456940979748,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 1386.172,
+      "eval_steps_per_second": 87.716,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 23.48023796081543,
+      "learning_rate": 4.154520119093442e-05,
+      "loss": 0.5672,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 34.38399124145508,
+      "learning_rate": 3.811284815136614e-05,
+      "loss": 0.5388,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 15.397554397583008,
+      "learning_rate": 3.468049511179787e-05,
+      "loss": 0.5675,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.596796035766602,
+      "learning_rate": 3.124814207222959e-05,
+      "loss": 0.5658,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7189152836799622,
+      "eval_matthews_correlation": 0.35221451726824415,
+      "eval_runtime": 0.816,
+      "eval_samples_per_second": 1278.13,
+      "eval_steps_per_second": 80.879,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.27866098284721375,
+      "learning_rate": 2.781578903266131e-05,
+      "loss": 0.488,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.25798484683036804,
+      "learning_rate": 2.438343599309304e-05,
+      "loss": 0.4217,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 25.567895889282227,
+      "learning_rate": 2.095108295352476e-05,
+      "loss": 0.4353,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.1678485870361328,
+      "learning_rate": 1.7518729913956483e-05,
+      "loss": 0.4524,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9973039031028748,
+      "eval_matthews_correlation": 0.394210256729861,
+      "eval_runtime": 0.8272,
+      "eval_samples_per_second": 1260.9,
+      "eval_steps_per_second": 79.789,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 97800525192492.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.87069663887758e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-1/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aee351340990176090794d80423bc66843abb9d835babac4ae2c2cf2a474913
+size 4984

run-1/checkpoint-8552/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd457bd8c81e8920cea04d50bb8020d2937d8f99772ad0902f7e943ceb90be2a
+size 267832560

run-1/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce41571c2ccacf472abe9c23e794c2206dca4e6711dafb72d86eab77d2e5ebce
+size 535727290

run-1/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403a670bfc46c070643881828093f7ac35633711652509c608e9ed937d0d4389
+size 14244

run-1/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c82a720df96003907bf53637e087933419f7a1885accba96ade8a32fc16bd0e
+size 1064

run-1/checkpoint-8552/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-8552/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-8552/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.394210256729861,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-6414",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.2052836418151855,
+      "learning_rate": 5.527461334920752e-05,
+      "loss": 0.6278,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5090547800064087,
+      "learning_rate": 5.1842260309639244e-05,
+      "loss": 0.6192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.86550760269165,
+      "learning_rate": 4.840990727007098e-05,
+      "loss": 0.6103,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.385833740234375,
+      "learning_rate": 4.49775542305027e-05,
+      "loss": 0.5852,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6027922034263611,
+      "eval_matthews_correlation": 0.15833456940979748,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 1386.172,
+      "eval_steps_per_second": 87.716,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 23.48023796081543,
+      "learning_rate": 4.154520119093442e-05,
+      "loss": 0.5672,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 34.38399124145508,
+      "learning_rate": 3.811284815136614e-05,
+      "loss": 0.5388,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 15.397554397583008,
+      "learning_rate": 3.468049511179787e-05,
+      "loss": 0.5675,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.596796035766602,
+      "learning_rate": 3.124814207222959e-05,
+      "loss": 0.5658,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7189152836799622,
+      "eval_matthews_correlation": 0.35221451726824415,
+      "eval_runtime": 0.816,
+      "eval_samples_per_second": 1278.13,
+      "eval_steps_per_second": 80.879,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.27866098284721375,
+      "learning_rate": 2.781578903266131e-05,
+      "loss": 0.488,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.25798484683036804,
+      "learning_rate": 2.438343599309304e-05,
+      "loss": 0.4217,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 25.567895889282227,
+      "learning_rate": 2.095108295352476e-05,
+      "loss": 0.4353,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.1678485870361328,
+      "learning_rate": 1.7518729913956483e-05,
+      "loss": 0.4524,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9973039031028748,
+      "eval_matthews_correlation": 0.394210256729861,
+      "eval_runtime": 0.8272,
+      "eval_samples_per_second": 1260.9,
+      "eval_steps_per_second": 79.789,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 30.455631256103516,
+      "learning_rate": 1.4086376874388207e-05,
+      "loss": 0.3968,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 23.722305297851562,
+      "learning_rate": 1.065402383481993e-05,
+      "loss": 0.2347,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 25.006427764892578,
+      "learning_rate": 7.221670795251653e-06,
+      "loss": 0.2626,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 10.499305725097656,
+      "learning_rate": 3.7893177556833777e-06,
+      "loss": 0.241,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 0.04408714175224304,
+      "learning_rate": 3.5696471611510076e-07,
+      "loss": 0.2334,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4050955772399902,
+      "eval_matthews_correlation": 0.36977195436601945,
+      "eval_runtime": 0.7541,
+      "eval_samples_per_second": 1383.157,
+      "eval_steps_per_second": 87.525,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 138657921014676.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.87069663887758e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-1/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aee351340990176090794d80423bc66843abb9d835babac4ae2c2cf2a474913
+size 4984

runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709519889.78dd22f13cdf.294.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf73eb11ca7057d9a3688f6d5c8d1d05856b56c17a50dc07887e367083dec33
-size 7128
+oid sha256:b078152514da2ced2b6337c88459e152f4c9ca0eb384200ac12a144925dc7241
+size 9840